- 13.3% of all cancer diagnoses.
- 7.1% of all cancer related deaths.
WHO Guide to cancer early diagnosis
- Early diagnosis and prognosis may aid treatment and focus resources where needed.
Introduction
Materials and methods
Materials
26 explanatory variables.
- Condition
- tumor type
| patient_id | gender | education | treatment_data | id_healthcenter | id_treatment_region | hereditary_history | birth_date | age | weight | thickness_tumor | marital_status | marital_length | pregnency_experience | giving_birth | age_FirstGivingBirth | abortion | blood | taking_heartMedicine | taking_blood_pressure_medicine | taking_gallbladder_disease_medicine | smoking | alcohol | breast_pain | radiation_history | Birth_control(Contraception) | menstrual_age | menopausal_age | Benign_malignant_cancer | condition |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 111036008041 | 0 | 4 | 2019 | 1.11e+09 | 1.11e+09 | 1 | 1989 | 30 | 69 | 0.90 | 1 | 0 | 0 | 0 | 0 | 0 | 4 | 0 | 1 | 1 | 0 | 0 | 1 | 1 | 1 | 1 | 0 | 1 | death |
| 111035996130 | 0 | 6 | 2019 | 1.11e+09 | 1.11e+09 | 0 | 1989 | 30 | 71 | 0.80 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | 1 | 1 | 0 | 1 | 0 | 0 | 0 | 2 | 0 | 0 | death |
| 111035971333 | 0 | 5 | 2019 | 1.11e+09 | 1.11e+09 | 0 | 1989 | 30 | 74 | 0.90 | 1 | 0 | 0 | 0 | 0 | 1 | 4 | 1 | 1 | 0 | 0 | 0 | 1 | 1 | 0 | 1 | 0 | 1 | death |
| 111036018485 | 0 | 5 | 2019 | 1.11e+09 | 1.11e+09 | 1 | 1989 | 30 | 75 | 0.70 | 1 | 1 | 1 | 3 | 1 | 0 | 2 | 1 | 1 | 1 | 1 | 0 | 0 | 0 | 0 | 2 | 0 | 0 | death |
| 111035985474 | 0 | 1 | 2019 | 1.11e+09 | 1.11e+09 | 0 | 2009 | 10 | 70 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 7 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | death |
| 111035903616 | 0 | 3 | 2019 | 1.11e+09 | 1.11e+09 | 1 | 1989 | 30 | 79 | 0.70 | 0 | 0 | 0 | 0 | 0 | 0 | 6 | 1 | 1 | 1 | 0 | 1 | 1 | 1 | 1 | 1 | 0 | 1 | death |
| 111036003507 | 0 | 4 | 2019 | 1.11e+09 | 1.11e+09 | 1 | 1990 | 29 | 96 | 0.10 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 | 1 | 0 | 0 | 0 | 1 | 1 | 0 | 2 | 0 | 1 | death |
| 111036026259 | 0 | 5 | 2019 | 1.11e+09 | 1.11e+09 | 0 | 1990 | 29 | 75 | 0.80 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | 0 | 1 | 0 | 0 | 0 | 2 | 0 | 0 | death |
Process
Cleaning the data
Unrealistic age and weight proportions.
Cleaning the data
| Changes |
|---|
| Column names |
| Removed special characters from variable names |
| Variable values |
| Greedy cleanup of binary variables: None binary values set to 1 |
| Blood type had one value of 44 (mistake) which was changed to NA |
| Birth dates of other than 4 numbers were set to NA |
| Filter out samples |
| Only include women as they are the risk group of breast cancer (few men are hit) |
| Only include women > 20 years, as they are the primary risk group |
| Remove samples with abnormal weight age proportions |
| Filter out a single woman who is set to not yet have her period, but have experience in pregnancy |
| Removing columns |
| Remove singular columns (with only one value for all samples) |
Augmenting the data
| Changes |
|---|
| Values changed |
| Categorical variables encoded with label and encoded as factor |
| Adding columns |
| Age at treatment |
| Normalised numerical variables |
Exploratory Analysis
Distributions
Distributions
Distributions
Distributions
MCA Tumortype
MCA Condition
MCA Rotation
Model
Predicting tumortype
Reduced Model
- Age (norm)
- Weight (norm)
- Hereditary history
- Smoking
- Radiation therapy
- Menstrual age
- Pregnancy experience
- Abortion
- Breast pain
| model | sensitivity | specificity | balanced_accuracy |
|---|---|---|---|
| Max_pred | 69% | 28% | 48% |
| Red_pred | 81% | 24% | 53% |
| baseline | 100% | 0% | 50% |
| Note: | |||
| Positive class = Malignant |
Predicting Condition
Reduced Model
- Age
- Gallbladder medicine
- Menopausal age
- Abortion
| model | sensitivity | specificity | balanced_accuracy |
|---|---|---|---|
| Max_pred | 89% | 36% | 63% |
| Red_pred | 92% | 33% | 63% |
| baseline | 100% | 0% | 50% |
| Note: | |||
| Positive class = Death |
Discussion & Conclusion
Discussion
- Greedy cleaning approach
- Disagreement between MCA and reduced model
- A general set of rules for valid entries
Conclusion
- Possible to predict both tumor type and outcome.
- The prediction accuracy.
- Shinny app
Bibliography
- 2020 Cancer incidence and mortality in EU-27 countries EU Science Hub
- WHO Guide to cancer early diagnosis World Health Organization. Cancer
- Breast Cancer Dataset Kaggle
- Breast cancer incidence (invasive) statistics (10 March 2020). Cancer Research UK
- Height Percentile Calculator for Men and Women in the United States DQYDJ
- Weight Gain After Breast Cancer Diagnosis May Be a Bigger Issue Than Thought in Australia (13 March 2020) Breastcancer.org
- Github Repository Group 9 Final Project
Shiny app
Shiny App
THANKS
FOR YOUR ATTENTION
Learning objectives
- Explain why reproducible data analysis is important, as well as identify relevant challenges and explain replicability versus reproducibility
- Describe the components of a reproducible data analysis
- Use Tidyverse R to perform exploratory data analysis (EDA) for data insights, including using ggplot to visualize multilayer data from e.g. high-througput -omics platforms
- Use Tidyverse R to perform data cleansing, transformation, visualization and communication
- Use RStudio and git/GitHub for collaborative analysis projects
- Perform and interpret standard dimension reduction and clustering techniques, as well as basic statistical tests and models